SOTAVerified

Image Classification

Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.

Source: Metamorphic Testing for Object Detection Systems

Papers

Showing 80268050 of 10420 papers

TitleStatusHype
Multimodal Semantic Transfer from Text to Image. Fine-Grained Image Classification by Distributional Semantics0
Deceiving Image-to-Image Translation Networks for Autonomous Driving with Adversarial Perturbations0
The troublesome kernel -- On hallucinations, no free lunches and the accuracy-stability trade-off in inverse problemsCode0
DAF-NET: a saliency based weakly supervised method of dual attention fusion for fine-grained image classification0
FrequentNet: A Novel Interpretable Deep Learning Model for Image ClassificationCode0
Improve Unsupervised Domain Adaptation with Mixup Training0
Kernelized Support Tensor Train Machines0
Training Deep Networks with Stochastic Gradient Normalized by Layerwise Adaptive Second Moments0
Test-Time Training for Generalization under Distribution Shifts0
Differentiable Architecture Compression0
Interpolation between CNNs and ResNets0
Inducing and Exploiting Activation Sparsity for Fast Inference on Deep Neural Networks0
UW-NET: AN INCEPTION-ATTENTION NETWORK FOR UNDERWATER IMAGE CLASSIFICATION0
Scalable NAS with Factorizable Architectural Parameters0
Recognizing Images with at most one Spike per Neuron0
RC-DARTS: Resource Constrained Differentiable Architecture Search0
Semi-Supervised Learning with Normalizing FlowsCode0
QDNN: DNN with Quantum Neural Network LayersCode0
Mixed-Precision Quantized Neural Network with Progressively Decreasing Bitwidth For Image Classification and Object Detection0
Deep Context-Aware Kernel Networks0
Active Learning in Video Tracking0
NAS evaluation is frustratingly hardCode0
Statistical Loss and Analysis for Deep Learning in Hyperspectral Image ClassificationCode0
Embedding of FRPN in CNN architecture0
Benchmarking Adversarial Robustness0
Show:102550
← PrevPage 322 of 417Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94Unverified
4DaViT-GTop 1 Accuracy90.4Unverified
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
6DaViT-HTop 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified